Generate custom images from text prompts via the MiniMax image-01 API.
npx skills add https://github.com/Sma1lboy/kobe --skill image-gen-sma1lboy
Please help me install this Agent Skill. Skill: image-gen Source: https://github.com/Sma1lboy/kobe/tree/main/.claude/skills/image-gen Command: npx skills add https://github.com/Sma1lboy/kobe --skill image-gen-sma1lboy
This skill solves the need for rapid, programmatic image generation directly from a terminal environment, eliminating the need to switch to external browser-based design tools.
Use the image-gen skill to create a 512 by 512 pixel flat vector icon of a robot and save it as robot.png.
High-intent search queries and answers about installing and using this skill.
You generate custom images from text prompts programmatically by sending descriptive text to the MiniMax image-01 API, which returns high-quality visual assets decoded as files using the requests library.
Yes, you can generate UI icons and illustrations without leaving your terminal. It processes text prompts to create visual assets like flat vector icons directly within automated design or documentation workflows.
Yes, the requests library is required to handle API communication and base64 decoding for file output when generating custom images from text prompts using the MiniMax image-01 model.
Yes, the text-to-image generation process supports specific customizable width and height dimensions, allowing you to create consistently sized visual assets for design prototypes and documentation.
The best way to programmatically create placeholder illustrations for documentation is using the MiniMax image-01 API to generate conceptual sketches from text prompts and decode the output as image files.
Programmatic image generation eliminates browser-based design tools by allowing you to generate custom images from text prompts directly from your terminal, integrating seamlessly into automated development workflows.
lxh755818-botGenerate images via the MiniMax Image-01 API using Python urllib.
tusososGenerate AI images from prompts using Google Gemini and save them to a specified path.
mbastakisBuild terminal user interfaces with Core, React, and Solid.
Team-AiltirGenerate SVG vector icons from text prompts aligned with Ailtir brand guidelines.
